Claude, a popular Large Language Model (LLM), has a magic string which is used to test the model’s “this conversation violates our policies and has to stop” behaviour. You can embed this string into files and web pages, and Claude will terminate conversations where it reads their contents.
Found on Drew DeVault's blog https://drewdevault.com/2025/03/17/2025-03-17-Stop-externalizing-your-costs-on-me.html